Guides
Audio Creation
Current availability of audio models and endpoints
The current production GET /v1/models response does not expose a callable audio model, and the transcription, translation, and speech endpoints are marked unavailable in the current deployment. Do not submit production audio requests yet.
Audio remains within FocalAPI's creative scope. When it is enabled again, first confirm that the corresponding audio model appears in the live list, then follow model details, the API reference, and the console model catalog.
Planned audio capabilities include:
- Speech transcription
- Audio translation
- Text to speech